Allowing spelling of arbitrary words
First Claim
Patent Images
1. A method comprising:
- transmitting, by data processing hardware, a transcription of a voice query over a network to a user device, the transcription of the voice query when received by the user device causing the user device to display the transcription of the voice query in a user interface of the user device;
receiving, at the data processing hardware, a correction input over the network from the user device, the correction input comprising;
a selection indication indicating a user selection in the user interface of a misrecognized term of the transcription of the voice query displayed in the user interface; and
a voice input from a user of the user device, the voice input including a series of letters that spells out a corrected term to replace the misrecognized term of the transcription of the voice query;
in response to receiving the correction input from the user device, generating, by the data processing hardware, an updated transcription of the voice query based on the voice input from the user of the user device; and
transmitting, by the data processing hardware, the updated transcription of the voice query over the network to the user device.
0 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.
21 Citations
20 Claims
-
1. A method comprising:
-
transmitting, by data processing hardware, a transcription of a voice query over a network to a user device, the transcription of the voice query when received by the user device causing the user device to display the transcription of the voice query in a user interface of the user device; receiving, at the data processing hardware, a correction input over the network from the user device, the correction input comprising; a selection indication indicating a user selection in the user interface of a misrecognized term of the transcription of the voice query displayed in the user interface; and a voice input from a user of the user device, the voice input including a series of letters that spells out a corrected term to replace the misrecognized term of the transcription of the voice query; in response to receiving the correction input from the user device, generating, by the data processing hardware, an updated transcription of the voice query based on the voice input from the user of the user device; and transmitting, by the data processing hardware, the updated transcription of the voice query over the network to the user device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 20)
-
-
11. A system comprising:
-
data processing hardware; and memory hardware in communication with the data processing hardware and storing instructions that when executed by the data processing hardware causes the data processing hardware to perform operations comprising; transmitting a transcription of a voice query over a network to a user device, the transcription of the voice query when received by the user device causing the user device to display the transcription of the voice query in a user interface of the user device; receiving a correction input over the network from the user device, the correction input comprising; a selection indication indicating a user selection in the user interface of a misrecognized term of the transcription of the voice query displayed in the user interface; and a voice input from a user of the user device, the voice input including a series of letters that spells out a corrected term to replace the misrecognized term of the transcription of the voice query; in response to receiving the correction input from the user device, generating an updated transcription of the voice query based on the voice input from the user of the user device; and transmitting the updated transcription of the voice query over the network to the user device. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
Specification